183 results about "Constant false alarm rate" patented technology

The invention discloses a fixed dual-runway FOD detection method based on multi-source circumferential scanning, and belongs to the technical field of data fusion detection, and the method specifically comprises the steps: synchronously obtaining dual-runway multi-polarization echo data through a fixed circumferential scanning rada; performing time-varying clutter suppression by combining an adaptive clutter cancellation method matched with a dynamic background template and a runway material feature library, and generating a time-frequency domain three-dimensional feature matrix through time-frequency analysis; synchronously collecting and preprocessing image data, and marking a target area through a constant false alarm rate algorithm and image detection; a multi-source data geographic coordinate mapping model is established, data registration and cross validation are completed under a runway physical coordinate system, and real-time tracking of a real FOD target is realized based on radar and image fusion data through multi-dimensional confirmation of radar polarization / micro-motion features and image visual features; according to the method, the FOD detection accuracy and the position identification precision are improved through multi-source data fusion, the false alarm rate is effectively reduced, and a guarantee is provided for safe operation of an airport.

The invention belongs to the technical field of wireless sensing and artificial intelligence, and discloses a high-robustness non-contact accurate electrocardiogram monitoring method based on a millimeter wave radar. Firstly, the distance and angle of a potential target are obtained through distance fast Fourier transform and digital beam forming technologies, and static background removal and thoracic cavity position detection are achieved in combination with mean filtering and a two-dimensional constant false alarm rate algorithm. And then a continuous phase is extracted by using a differential cross multiplication method, a two-step heartbeat-related phase extraction scheme is designed, body micro-motion and breathing interference are removed by adopting B-spline fitting and differential operation respectively, and a stable heartbeat-related phase signal is obtained. A heart rate-guided adaptive wavelet decomposition method is designed to obtain multiband features, and time-frequency joint features are extracted through a double-branch attention mechanism and a gating fusion part. Finally, the time-frequency joint features are input into an electrocardiosignal time domain reconstruction module based on a TransUNet architecture, high-quality reconstruction of electrocardiosignals is achieved, and the method has the advantages of being non-contact, continuous and convenient.

The invention relates to the technical field of radar signal processing, and discloses a complex ground reflection environment-oriented dual-path target detection method, which comprises the following steps of: performing quantile truncation and discretization processing on original range profile data, mapping a processed signal to a D-channel discrete feature space and generating a D-dimensional discrete feature matrix; the D-dimensional discrete feature matrix is input into a dual-channel parallel processing architecture, a CFAR adaptive detection module is adopted in a first path to suppress strong clutters to generate a first response matrix, and a false attention mechanism is adopted in a second path to enhance weak targets to generate a second response matrix; performing spatial alignment and weighting processing on the first response matrix and the second response matrix, and performing cross-domain confidence fusion to output a comprehensive response matrix; and carrying out fixed threshold binarization processing on the comprehensive response matrix based on a global threshold to obtain a target detection result. The method has both local gain compensation and global adaptive suppression, and can realize more robust detection of a weak target under a complex background.

The invention provides an ultrasonic three-dimensional imaging method and system based on an FPGA, and relates to the technical field of ultrasonic imaging, and the method comprises the steps: transmitting a chirp signal, receiving an echo signal reflected by a target object, and carrying out the preprocessing; carrying out adaptive filtering, constant false alarm rate detection, adaptive beam forming and three-dimensional positioning algorithm processing on the preprocessed signal to generate target position data; and performing three-dimensional point cloud image reconstruction on the target position data by using a density-based spatial clustering algorithm and a deep learning model, and outputting a target three-dimensional image. Through the innovation of a signal processing algorithm and the collaborative design of the system, the technical bottlenecks of a traditional ultrasonic sensor in detection distance, anti-interference, real-time performance and positioning precision are solved, and the three-dimensional sensing capability with high reliability and strong environmental adaptability is provided for intelligent driving.

The present invention discloses a radar CFAR target detection method based on the prefix sum algorithm. The method performs Fourier transform and square-law detection on the radar echo signal to obtain the range-Doppler matrix A, and performs constant false alarm rate (CFAR) processing on the range-Doppler matrix A to determine whether a target exists. When performing CFAR detection, a rectangular reference sliding window is used. First, the prefix sum algorithm is used to obtain the prefix sum matrix SUM of the range-Doppler matrix A, and then the average value of the data of the surrounding reference cells of the cell a to be measured is calculated through the prefix sum matrix. The average value is multiplied by a coefficient to obtain an estimated value of the background clutter, and the estimated value is compared with the cell to be detected to determine whether the cell to be detected is a target. The method of the present invention ensures the accuracy of detection while reducing the complexity of the algorithm, reducing the computational amount of the original CFAR detection, and improving the detection efficiency. i,j The method of the present invention ensures the accuracy of detection while reducing the complexity of the algorithm, reducing the computational amount of the original CFAR detection, and improving the detection efficiency.

A non-contact real-time monitoring system of physiological signs based on millimeter-wave radar includes a millimeter-wave radar and multiple modules for processing radar signals. The millimeter-wave radar is configured to continuously transmit electromagnetic wave signals and simultaneously receive echo signals, perform frequency mixing processing on the echo signals to obtain an intermediate frequency signal, and process the intermediate frequency signal to obtain a radar four-dimensional data matrix. Human body physiological signs are monitored by analyzing body thoracic cavity micro-motion information in signals through the modules; a target echo is processed by adopting a constant false alarm rate detection algorithm, and invalid signals are filtered. A self-adaptive range cell selection algorithm based on short-time stability of respiratory signals is adopted to capture radar echoes reflecting physiological movement. Mixed human body physiological sign signals are processed by using a VMD algorithm, and key parameters in VMD are optimized by using a GWO algorithm.

The invention discloses a clustering algorithm for Terahertz radar extended target tracking. The clustering algorithm comprises three steps of drawing an azimuth distance map by using original data, carrying out two-dimensional unit average constant false alarm rate detection on an azimuth distance dimension, and clustering by a connected domain labeling method. In the first step, a grid interpolation method is used for carrying out zero interpolation on the reflection intensity of discrete points, so that subsequent calculation of background noise is facilitated; in the second step, a threshold value is calculated by setting related parameters, and part of clutter interference is filtered out; in the third step, adjacent data points are communicated through an eight-field method, then morphological closed operation is designed to merge adjacent targets, the problem of excessive segmentation is effectively avoided, then a minimum area threshold value is added to filter clutter interference, effective targets are reserved, and finally the clustering effect is more remarkable through target center point labeling. The clustering algorithm for Terahertz radar extended target tracking is low in cost, high in processing speed and remarkable in effect, and has certain application value in the fields of Terahertz radar extended target tracking and the like.

The invention relates to the technical field of urban low-altitude safety monitoring, and discloses a low-altitude economic airspace passive safety early warning method and system. The method comprises the following steps: collecting multi-modal observation data streams of a target at different moments; generating multi-modal frame data with a unified timestamp; establishing a spatial confidence distribution map; extracting fusion discrimination features; executing multi-channel small target detection; continuously tracking the preliminary target; and introducing a constant false alarm rate framework to set a dynamic confidence threshold to execute alarm judgment. Compared with the prior art, the technical problem that high-confidence all-weather passive monitoring cannot be realized in urban core areas with dense buildings, serious signal shielding and easy GPS failure due to dependence on single vision or radar information in the prior art is solved. According to the method, the space confidence distribution diagram and the dynamic constant false alarm mechanism based on the shielding diagram are constructed by fusing the multi-modal sensing data, so that the safety early warning of the low-altitude small aircraft is realized, and the passive safety guarantee capability of the low-altitude economic airspace is improved.

The invention discloses an improved self-adaptive CFAR (Constant False Alarm Rate) detection method for defects of worsted wool fabric, and relates to the technical field of defect detection of worsted wool fabric. The invention relates to an improved self-adaptive CFAR (Constant False Alarm Rate) detection method for defects of worsted wool fabric. The method comprises the following steps: shooting a color image of the worsted wool fabric by adopting a CCD (Charge Coupled Device) camera; converting the acquired color image into a grayscale image to obtain a grayscale value of each pixel; traversing the target grayscale image pixel by pixel by using a sliding window type CFAR detector; wherein the sliding window comprises a front edge sliding window and a rear edge sliding window; the combination of the leading edge sliding window and the trailing edge sliding window is used as a reference unit. According to the scheme, through the double-sliding-window structure design and the mean value self-adaptive selection algorithm, the false detection problem of the light and shade junction area is accurately restrained, and the false detection rate is remarkably reduced; the technical bottleneck that the false detection rate is high due to the fact that the fabric is uneven is broken through, double optimization of the false detection rate and the detection rate is achieved in a complex industrial scene, and a reliable technical scheme is provided for intelligent quality inspection of the worsted fabric.

The invention discloses an unmanned aerial vehicle spectrum anomaly detection and trajectory generation method based on unsupervised learning, and the method comprises the steps: continuously collecting broadband radio frequency signals through an SDR, and obtaining an IQ data stream; performing short-time Fourier transform to obtain a time-frequency spectrogram; performing robust normalization processing on the time-frequency spectrogram to obtain a standardized spectrogram after slow-varying drift suppression; performing constant false alarm rate detection, and generating a primary abnormal candidate binary mask; identifying spectrogram sub-blocks corresponding to the primary abnormal candidate binary masks from the standardized spectrogram, and inputting the spectrogram sub-blocks into a pre-trained unsupervised deep learning model to obtain an abnormal scoring graph; fusing with the primary abnormal candidate binary mask to generate an abnormal heat map; and clustering the abnormal heat map in a time-frequency dimension, carrying out cross-time window trajectory association and filtering on a cluster, and outputting a time-frequency trajectory of the unmanned aerial vehicle signal. According to the invention, the reliability of anomaly detection is enhanced, the risk of false detection and missing detection is reduced, and the continuity and accuracy of track generation are guaranteed.

The invention discloses a generalized clutter texture distribution-oriented extended target full-adaptive constant false alarm rate detection method, which belongs to the field of radar signal processing, and comprises the following steps of: constructing test statistics according to texture distribution knowledge, covariance matrix structure information, signal subspace and the like; establishing an interpolation function of a threshold offline by using a Monte Carlo method, and estimating a corresponding threshold quickly and precisely according to parameters of a probability density function of a texture component; in a radar target detection process, unknown parameters in texture distribution are estimated by using a second group of training data, a full-adaptive detector is constructed by combining an interpolation function of test statistics and a threshold, and the detector is ensured to have a constant false alarm rate property for the parameters of the texture distribution and the change of a clutter covariance matrix. Compared with a traditional radar target detection method, the cognitive ability of a radar system to a complex environment is remarkably improved, and the method has good engineering application value and popularization potential.

The invention provides a target detection method and device based on a millimeter wave radar, and a control unit, and relates to the technical field of radar signal processing. The method comprises the steps that a first thermodynamic diagram corresponding to a detection area of the millimeter wave radar is acquired, the first thermodynamic diagram is divided at equal intervals in the speed dimension, multiple sub-bands are obtained, and the multiple sub-bands comprise a non-empty band and at least two empty bands; performing fusion processing on the plurality of sub-bands to obtain a second thermodynamic diagram; based on a constant false alarm rate algorithm, according to the second thermodynamic diagram, determining a detection point trace corresponding to a real target in the targets; and determining the actual distance and the actual speed of the real target relative to the millimeter wave radar based on the detection trace and according to the phase offset of the transmitting antenna. According to the method, energy in the sub-bands is accumulated in a sub-band segmentation and fusion mode, so that the spectrum peak value of the real target is more prominent, the signal-to-noise ratio of the real target is effectively improved, the probability of occurrence of a false target is reduced, and the target detection precision is improved.

The invention provides a constant false alarm target detection method and device for an airborne random pulse repetition interval radar system, and relates to the technical field of radar signal processing. The method comprises the following steps: estimating a target scene through a compressed sensing model according to an echo sampling result and an observation matrix to obtain an estimation result of the target scene; taking a constant detected false alarm rate as a target, and constructing test statistics according to an echo sampling result, the observation matrix and an estimation result; performing threshold calculation based on chi-square distribution according to a preset expected false alarm rate and the test statistics to obtain a detection threshold; based on the support set definition of the clutter region, calculating according to the information of the receiving platform to obtain the position of the clutter region; and based on the clutter region position, according to the test statistics and the detection threshold, performing target position detection on a region outside the clutter region to obtain a target position. The method is an efficient and accurate constant false alarm target detection method for an airborne random pulse repetition interval radar.

The invention discloses an active sonar target identification method based on message passing multi-hypothesis tracking, and belongs to the technical field of underwater target detection. The method comprises the following steps: firstly, processing single-cycle sonar data by using adaptive constant false alarm detection, obtaining observation points, and forming an effective observation set through hierarchical clustering; thirdly, extrapolating the existing target, calculating the association probability of the existing target and the current observation by adopting a message passing method, and generating a plurality of groups of association hypotheses; then, the target state is corrected through Kalman filtering, target rejection and new management are executed, and a high-probability hypothesis is reserved; and finally, estimating the motion speed based on the target multi-period position sequence, and distinguishing a static object from a suspicious motion target according to a speed threshold. Through the multi-hypothesis tracking and probability message passing mechanism, clutter interference and static target influence in a complex underwater environment are effectively overcome, and the stability of target tracking, the accuracy of speed estimation and the overall reliability of system identification are remarkably improved.

The invention relates to the technical field of intelligent sensors, in particular to an unmanned aerial vehicle track intelligent tracking method based on a millimeter-wave radar, which comprises the following steps: receiving echo signals collected by the front end of the millimeter-wave radar, carrying out constant false alarm rate detection and Doppler frequency shift extraction on the echo signals, generating an unmanned aerial vehicle target space coordinate set, and carrying out target tracking on the unmanned aerial vehicle. And mapping the target space coordinate set of the unmanned aerial vehicle to a three-dimensional Euclidean space. According to the method, a non-convex optimization objective function containing beam switching time cost and precision constraint is constructed, and mathematical optimal solution of radar beam resources is realized. The generated adaptive scheduling instruction is used for adjusting the pulse repetition frequency and the beam residence time, it is ensured that radar front-end parameters dynamically evolve along with the target state, overall centroid tracking is emphasized for rigid body formation so as to save resources, independent high-frequency refreshing is emphasized for discrete targets so as to ensure the precision, and the accuracy is improved. And the continuity and robustness of trajectory tracking of the unmanned aerial vehicle in a complex electromagnetic environment are improved.

The present disclosure provides a constant false alarm rate-based downhole casing nondestructive testing method, device and medium. The method can include: obtaining a detection threshold according to a preset false alarm probability and background noise power of a target pulsed eddy current array detection signal, wherein the false alarm probability refers to the probability that the detection system incorrectly determines the presence of a damaged target when a non-damaged target is present in the downhole casing; screening the target pulsed eddy current array detection signal based on the detection threshold to obtain a downhole casing damage detection result signal; and determining the position of the downhole casing damage according to the downhole casing damage detection result signal. Through this technical solution, the detection threshold can be dynamically adjusted, and the position of the downhole casing damage can be accurately located, thereby improving the efficiency and accuracy of downhole casing damage detection.

The invention discloses an anti-high dynamic Doppler low signal-to-noise ratio satellite signal blind detection method, which comprises the following steps of: performing frequency domain analysis on a delay correlation signal according to a signal symbol rate, and dividing a signal band and a noise band near the delay correlation signal to construct a detection quantity to perform constant false alarm rate (CFAR) detection; and finally, obtaining a final signal existence or disappearance result through time consistency judgment. According to the method disclosed by the invention, the analytic CFAR threshold and the state machine smoothing are combined, and the problem of detection failure in a low signal-to-noise ratio and high dynamic Doppler environment in the prior art is solved.

The invention relates to a multichannel real-time processing method and device for ultrahigh frequency river detection radar signals. The method comprises the following steps: synchronously sampling analog echo data of multiple channels to obtain a digital echo signal; based on the digital echo data, pulse compression processing is carried out, and baseband multi-channel data is output; performing memory scheduling processing on the baseband multichannel data based on a ping-pong buffer strategy to obtain continuous data blocks; based on a preset adaptive filtering weight, performing partition adaptive weighted summation filtering on the continuous data blocks to generate a clutter suppressed single-channel data matrix; performing constant false alarm rate detection based on the single-channel data matrix to obtain a target detection list; and based on the target detection list, performing visual rendering, and generating a radar detection report of the river detection radar for detection. By adopting the method, clutters can be effectively suppressed, and the credibility of the river detection radar signal is improved.

The application provides a hypersonic platform radar target detection method, device and electronic equipment, relates to the technical field of hypersonic radar target detection, and the method comprises the following steps: inputting a received first echo signal into a time domain echo signal model, converting the first echo signal from a first signal domain to a second signal domain by using the time domain echo signal model, and obtaining a second echo signal; filtering the second echo signal by using an optimal parameter filter, obtaining a filtered third echo signal, converting the third echo signal into a third signal domain, and obtaining a coherent accumulation result; determining whether a target is detected by using a constant false alarm rate detection based on the coherent accumulation result, and determining the distance of the target based on the position of a peak value in the accumulation result in the case that it is determined that the target is detected. The hypersonic platform radar target detection method, device and electronic equipment provided by the application can realize high-precision, high-efficiency and highly adaptable radar target detection.

The present invention belongs to the technical field of maritime target detection, and particularly relates to a two-dimensional constant false alarm target detection method and detector based on dual-observation-channel data. The method includes: obtaining the echo time series transmitted on each observation channel and received on each range cell; the observation channels include two observation channels of the cell to be detected and two observation channels of the reference cell; respectively performing square-law detection on the received echo time series to obtain detection statistics; calculating the estimated values of the clutter power levels of the two observation channels respectively based on the samples after square-law detection of the echo data of the reference cell; calculating the normalization factor according to the preset false alarm probability; and performing target detection according to the detection statistics, the estimated values of the clutter power levels, and the normalization factor, in combination with the two-dimensional constant false alarm adaptive decision criterion. It reduces the missed detection or misjudgment caused by the limitation of single-channel information, and improves the accuracy of judging the presence or absence of a target.

The invention discloses a sea surface small target detection method and system based on a magnetic KNN and an optimized concave packet, and belongs to the technical field of radar signal processing. Comprising the following steps: extracting high-dimensional features of sea clutters and echoes to be detected, and selecting three-dimensional feature points of the clutters and the echoes to be detected according to a dimension reduction algorithm; processing the three-dimensional feature points of the clutters by adopting a constant false alarm algorithm to obtain clutter feature points after constant false alarm; on the basis of the clutter feature points after the constant false alarm, constructing a concave packet by adopting an optimized concave packet construction algorithm; the clutter feature points in the concave packet serve as vertexes of a tetrahedron, and the concave packet is divided into tetrahedral grids; positioning the points in the tetrahedrons by using a pointLocation function, judging the indexes of the tetrahedrons where the points are located, and if the indexes exist, judging that the points are clutters; and if the index does not exist, judging as a target. According to the detection method, the construction efficiency of the concave packet is also improved while the relatively high detection probability is ensured, and the method has relatively good generalization.

The present invention discloses a multi-channel coherent accumulation method of an FDA-MIMO radar based on range-frequency offset compensation, which belongs to the technical field of radar moving target detection. The present invention comprises: obtaining the echo signal of the target by using a two-dimensional planar array FDA-MIMO radar; performing multi-channel matched filtering on the echo signal, and performing FFT transformation in slow time to realize pulse accumulation; then performing covariance matrix calculation to obtain the noise subspace and signal subspace; then performing azimuth and elevation angle search of the target, and obtaining the range-frequency offset coupling compensation vector based on eigendecomposition; multi-channel beamforming, coherently synthesizing the multi-channel signal energy and using a constant false alarm rate to detect the target. The present invention can significantly improve the output signal-to-noise ratio and reduce the computational complexity of coherent accumulation. Moreover, when there is an error in the target distance estimation or the Doppler effect is generated by the frequency offset, the present invention can obtain a higher coherent accumulation gain than the MUSIC algorithm.

The present application relates to the field of signal processing, deep learning and radar target detection, and particularly relates to a radar target detection method based on shallow and deep feature fusion. The present application solves the problem of poor detection generalization caused by relying on shallow features in the prior art by fusing shallow multi-domain features and deep learning features. The shallow features are subjected to multi-domain analysis, weighting and normalization processing, enhancing the ability to distinguish target echoes and sea clutter. The deep features are extracted by 1D-ResNet50 and spliced with the shallow features, combining physical meaning and expression ability, and improving the feature representation ability of the model. Combined with the constant false alarm rate algorithm, the detection threshold is dynamically adjusted to ensure stability and robustness in complex marine environments. The present application significantly improves the accuracy, generalization and practicality of target detection, and has high engineering application value.

The invention belongs to the technical field of radar signal processing, and particularly relates to a self-adaptive constant false alarm radar target detection method and system based on grouping and sequencing, and the method comprises the steps: extracting signal values of a to-be-detected unit and a reference unit thereof through receiving a radar echo signal; and according to the environmental background characteristics, adaptively selecting a processing strategy of direct sorting without grouping or sorting after averaging by grouping, and after an ordered sequence is generated, dynamically selecting the kth statistical magnitude to calculate a detection threshold. And respectively adopting different parameter adaptive mechanisms for the uniform background and the multi-target background: determining a k value by maximizing an expected value of a detection target number under the uniform background, and dynamically adjusting the k value and a grouping number n according to an interference target number under the multi-target background. According to the method, grouping processing and adaptive parameter selection are innovatively combined, the problem that the detection performance of a traditional CFAR algorithm is reduced in a complex environment is effectively solved, and the detection probability in a multi-target scene can be remarkably improved while the constant false alarm rate is kept.

The invention relates to a radar target detection and tracking technology, and provides a sky wave over-the-horizon radar particle filter track-before-detect method in order to solve the limitation of the traditional particle filter under long-time accumulation, a virtual frame and a speed interval are divided through motion constraint to obtain a plurality of parallel processing channels, so that a coherent pulse number estimation interval is reduced, and the estimation precision is improved. And coherent processing is carried out. Meanwhile, particles are randomly generated only in a distance-Doppler unit exceeding a threshold through a unit average constant false alarm rate CA-CFAR method before particle filtering processing, and the number of particles is further reduced. According to the method, the operand is reduced, and the weak target detection and tracking capability of the OTH radar is improved. According to the method, echo data preprocessing and coherent and non-coherent processing technologies are combined, and the calculation complexity is reduced while the detection and tracking performance of the weak target under the sky wave over-the-horizon radar is improved by means based on multiple channels and a low threshold.

The application provides a terrain awareness and warning system excessive descent rate warning constant false alarm rate detection method, comprising the following steps: step 1: calculating the no-alarm trajectory data of an airplane according to the flight parameters of the airplane; calculating the post-alarm trajectory data of the airplane; performing collision detection on the no-alarm flight trajectory and the post-alarm flight trajectory with a first-order Markov random terrain to determine whether a successful alarm or an unnecessary alarm is generated; step 2: using a Monte Carlo method to perform a large number of simulations, counting the successful alarm rate and the false alarm rate to generate an SOC curve, and selecting an optimal alarm threshold point; step 3: selecting a constant false alarm rate range according to the obtained optimal alarm threshold point; obtaining the relationship between the descent rate and the alarm height from the selected constant false alarm rate; and step 4: repeating step 3 to obtain an optimal constant false alarm rate. The application can effectively reduce the false alarm rate of the excessive descent rate mode alarm, increase the safe flight probability, and adapt to more flight conditions.

The present invention belongs to the field of radar constant false alarm detection and relates to a constant false alarm detection method based on background discrimination. The method of the present invention adopts the idea of deleting constant false alarm detection, ensuring the detection probability in the case of target occlusion, so that the detection probability of the present invention is higher in the case of target occlusion. The present invention calculates the clutter separation point within the full detection range, further improving the stability of the false alarm probability near the clutter demarcation point and enhancing the detection performance. By adopting different detection strategies in different situations, the method of the present invention can achieve target detection under multi-target interference and improve the stability of the false alarm probability at the clutter edge.

The invention relates to the technical field of millimeter wave radars, and discloses a millimeter wave signal reconstruction method and system for indoor monitoring and a storage medium. The method comprises the following steps: acquiring video frame data of a target object and original I / Q data acquired by a millimeter wave radar, extracting key feature data of the target object from the video frame data, and mapping the key feature data to a radar coordinate system to form human body prior information; preprocessing the original I / Q data to obtain an amplitude matrix and a phase matrix, performing normalization processing on the amplitude matrix based on a noise baseline, and combining with the phase matrix to generate radar echo data; establishing a prior drive mapping model based on the two modes, and performing enhancement processing on the radar echo data to obtain enhanced radar echo data; and a binary detection map is generated by applying constant false alarm rate detection, the target object is tracked by adopting Kalman filtering, the motion trail information of the target object is obtained, and the accuracy of indoor area target object detection is improved.

The invention provides a target detection method and system, a storage medium and electronic equipment. The target detection method comprises the following steps: acquiring a distance Doppler spectrum of a detection radar, and performing initial target detection according to the distance Doppler spectrum to obtain a first detection target signal; performing channel separation on a transmitting channel of the detection radar based on the first detection target signal to obtain a second detection target signal; performing constant false alarm rate detection based on the second detection target signal to obtain a third detection target signal; and carrying out association matching on the secondary false target rejection result and the previous frame of target signal, so as to obtain a final detection target signal based on an association matching result and the third detection target signal. According to the invention, false target elimination can be realized under the condition of limited storage space or computing power resources, and weak and small target detection can be realized at the same time.

The invention provides a millimeter-wave radar cross-environment perception generalization method and system based on course learning, and relates to the technical field of millimeter-wave radar perception, and the method comprises the steps: carrying out the constant false alarm rate detection of a distance velocity spectrogram obtained through preprocessing, and carrying out the interception to obtain a most easy sample data set; carrying out course learning stage progressive learning on the most likely sample data set to obtain a training stage total number and a training stage sample range of a millimeter wave radar cross-environment perception generalization model constructed by introducing a self-adaptive feature map down-sampling mechanism, and training the millimeter wave radar cross-environment perception generalization model; obtaining a trained millimeter wave radar cross-environment perception generalization model; and inputting to-be-identified millimeter-wave radar data into the millimeter-wave radar cross-environment perception generalization model, and outputting an environment perception identification result of the to-be-identified millimeter-wave radar data. According to the method, millimeter wave radar perception has cross-environment generalization capability, and the identification precision in an unknown scene is improved.